Papers with Code · CC BY-SA 4.0

HMDB51

아카이브 평가 45건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
MVD (ViT-B)	Top-1 Accuracy 79.7 Pre-Training Dataset Kinetics400 Frozen false	Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning 2022-12-08	코드 1 · 코드 2 · 코드 3 · 코드 4
M3Video	Top-1 Accuracy 78.0 Pre-Training Dataset Kinetics400 Frozen false	Masked Motion Encoding for Self-Supervised Video Representation Learning 2022-10-12	코드 1 · 코드 2
pBYOL	Top-1 Accuracy 75.0 Pre-Training Dataset Kinetics400 Frozen false	A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning 2021-04-29	코드 1 · 코드 2
SCE (R3D-50)	Top-1 Accuracy 74.7 Pre-Training Dataset Kinetics400 Frozen false	Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning 2022-12-21	코드 1 · 코드 2
VideoMAE	Top-1 Accuracy 73.3 Pre-Training Dataset Kinetics400 Frozen false	VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training 2022-03-23	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
BraVe:V-FA (TSM-50x2)	Top-1 Accuracy 70.5 Frozen false	Broaden Your Views for Self-Supervised Video Learning 2021-03-30	코드 1
CVRL (R3D-152 2x; K600)	Top-1 Accuracy 69.9 Pre-Training Dataset Kinetics600 Frozen false	Spatiotemporal Contrastive Video Representation Learning 2020-08-09	코드 1 · 코드 2 · 코드 3 · 코드 4
XKD (ViT-B/112/16)	Top-1 Accuracy 69	XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning 2022-11-25	코드 1
XDC	Top-1 Accuracy 52.6 Pre-Training Dataset Kinetics400 Frozen false	Self-Supervised Learning by Cross-Modal Audio-Video Clustering 2019-11-28	코드 1
CVRL (R3D-50; K600)	Top-1 Accuracy 68.0 Pre-Training Dataset Kinetics600 Frozen false	Spatiotemporal Contrastive Video Representation Learning 2020-08-09	코드 1 · 코드 2 · 코드 3 · 코드 4
CrissCross (AudioSet)	Top-1 Accuracy 66.8 Pre-Training Dataset AudioSet Frozen false	Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity 2021-11-09	코드 1
CVRL (R3D-50; K400)	Top-1 Accuracy 66.7 Pre-Training Dataset Kinetics400 Frozen false	Spatiotemporal Contrastive Video Representation Learning 2020-08-09	코드 1 · 코드 2 · 코드 3 · 코드 4
XKD-Modality-Agnostic (ViT-B/112/16)	Top-1 Accuracy 65.9	XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning 2022-11-25	코드 1
VideoMS (ViT-B)	Top-1 Accuracy 65.8 Pre-Training Dataset no extra data Frozen false	EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens 2022-11-19	코드 1 · 코드 2
AVID+CMA (Modified R2+1D-18 on Audioset)	Top-1 Accuracy 64.7 Pre-Training Dataset Audioset (Video+Audio) Frozen false	Audio-Visual Instance Discrimination with Cross-Modal Agreement 2020-04-27	코드 1
RSPNet	Top-1 Accuracy 64.7 Pre-Training Dataset Kinetics400 Frozen false	RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning 2020-10-27	코드 1
CrissCross (Kinetics400)	Top-1 Accuracy 64.7 Pre-Training Dataset Kinetics400 Frozen false	Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity 2021-11-09	코드 1
ELo	Top-1 Accuracy 64.5 Frozen false	Evolving Losses for Unsupervised Video Representation Learning 2020-02-26	연결 없음
AVID (Modified R2+1D-18 on Audioset)	Top-1 Accuracy 64.1 Pre-Training Dataset Audioset (Video+Audio) Frozen false	Audio-Visual Instance Discrimination with Cross-Modal Agreement 2020-04-27	코드 1
VideoMAE(no extra data)	Top-1 Accuracy 62.6 Pre-Training Dataset no extra data Frozen false	VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training 2022-03-23	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
ViCC (S3D; R+F)	Top-1 Accuracy 62.2 Pre-Training Dataset UCF101 Frozen false	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting 2021-06-18	코드 1
ViCC (R2+1D; R+F)	Top-1 Accuracy 61.5 Pre-Training Dataset UCF101 Frozen false	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting 2021-06-18	코드 1
AVID+CMA (Modified R2+1D-18 on Kinetics)	Top-1 Accuracy 60.8 Pre-Training Dataset Kinetics400 (Video+Audio) Frozen false	Audio-Visual Instance Discrimination with Cross-Modal Agreement 2020-04-27	코드 1
CrissCross (Kinetics-Sound)	Top-1 Accuracy 60.5 Pre-Training Dataset Kinetics-Sound Frozen false	Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity 2021-11-09	코드 1
AVID (Modified R2+1D-18 on Kinetics)	Top-1 Accuracy 59.9 Pre-Training Dataset Kinetics400 (Video+Audio) Frozen false	Audio-Visual Instance Discrimination with Cross-Modal Agreement 2020-04-27	코드 1
MCN (R3D-18; RGB)	Top-1 Accuracy 54.8 Pre-Training Dataset UCF101 Frozen false	Self-Supervised Video Representation Learning with Meta-Contrastive Network 2021-08-19	연결 없음
MCN (R2+1D; RGB)	Top-1 Accuracy 54.5 Pre-Training Dataset UCF101 Frozen false	Self-Supervised Video Representation Learning with Meta-Contrastive Network 2021-08-19	연결 없음
SLIC (R3D-18)	Top-1 Accuracy 54.5 Pre-Training Dataset UCF101 Frozen false	SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos 2022-06-25	코드 1
TCLR (R3D-18)	Top-1 Accuracy 52.9 Pre-Training Dataset UCF101 Frozen false	TCLR: Temporal Contrastive Learning for Video Representation 2021-01-20	코드 1
ViCC (R2+1D; RGB)	Top-1 Accuracy 52.4 Pre-Training Dataset UCF101 Frozen false	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting 2021-06-18	코드 1